WO2019007038A1

WO2019007038A1 - Floor sweeping robot, floor sweeping robot system and working method thereof

Info

Publication number: WO2019007038A1
Application number: PCT/CN2018/073868
Authority: WO
Inventors: 杨锴; 丁璜; 郑卓斌
Original assignee: 广东宝乐机器人股份有限公司
Priority date: 2017-07-05
Filing date: 2018-01-23
Publication date: 2019-01-10
Also published as: CN109213137A

Abstract

A floor sweeping robot (1), comprising a control system (150), a binocular camera (110), and an image processing system (140). The binocular camera (110) is used for acquiring two pieces of picture information at different angles of a same obstacle at the same moment; the image processing system (140) is used for processing the two pieces of picture information acquired by the binocular camera (110) to obtain obstacle information; the control system (150) executes different actions according to the obstacle information, wherein the obstacle information comprises the size and shape of the obstacle, and the distance between the obstacle and the floor sweeping robot (1). In addition, also disclosed are a floor sweeping robot system and a working method of the floor sweeping robot (1).

Description

Sweeping robot, sweeping robot system and working method thereof

Technical field

The invention relates to the field of indoor sweeping robots, in particular to a sweeping robot with obstacle recognition and a working method thereof.

Background technique

Most of the obstacle detection in the market for sweeping machines uses ultrasonic, infrared, mechanical collision switches (industrial terms referred to as front or front collision) and laser radar, or a combination of the above; among them, mechanical collision switches can only detect obstacles. The presence or absence of ultrasound, infrared, and laser radar (TOF ranging) is to calculate the time difference between the active transmitted signal and the received echo signal to achieve distance measurement. This method has limited detection range for obstacle detection. The target obstacle information is incomplete and the system expandability is weak. The specific performance is that only the distance from the two-dimensional work plane to the sweeper itself can be measured. It is impossible to measure the three-dimensional size of the obstacle, and it is easy to push and pull obstacles and climb obstacles. The condition of the object or stuck under the obstacle.

With the development of computer hardware and advances in image processing technology, it has become possible to use binocular cameras on the sweeper to identify obstacles in the work area.

Summary of the invention

In order to solve the technical problem in the background art, the present invention provides a cleaning robot, and the specific technical solutions are as follows:

A sweeping robot comprising a control system, a binocular camera and an image processing system;

The binocular camera is configured to acquire two picture information of different angles of the same obstacle at the same time;

The image processing system is configured to process two picture information acquired by the binocular camera and obtain obstacle information;

The control system performs different actions based on the obstacle information.

Further, the obstacle information includes an obstacle size, an obstacle shape, and a distance between the obstacle and the cleaning robot.

Further, a drive system is further included;

The driving system is configured to drive the cleaning robot to move in a work area;

When the obstacle size of the obstacle information is not greater than a preset value, the control system controls the driving system to increase the driving force, so that the sweeping robot crosses the obstacle;

When the obstacle size of the obstacle information is greater than a preset value, the control system controls the drive system to cause the sweeping robot to bypass the obstacle along the obstacle contour.

Further, a cleaning system is also included;

The cleaning system is used to clean the garbage and store it to the dust box;

When judging that the current obstacle is a blanket based on the obstacle information, the control system controls the driving system to increase the driving force, causing the cleaning robot to cross the blanket; and controlling the cleaning system to increase the cleaning power;

When it is determined that the current obstacle is garbage based on the obstacle information, the control system controls the driving system to move the cleaning robot to the garbage; and controls the cleaning system to perform cleaning.

Further, the binocular camera is an image sensor.

Further, the binocular camera is relatively fixedly mounted on the front end surface of the cleaning robot and the two cameras of the binocular camera are installed at the same horizontal position.

In order to solve the technical problem in the background art, the present invention also provides a cleaning robot, and the specific technical solutions are as follows:

A sweeping robot, including a binocular camera, a wireless communication system, and a control system;

The wireless communication system is configured to transmit two pieces of the picture information to the outside, and is further configured to receive externally transmitted obstacle information;

Further, a drive system is further included;

Further, a cleaning system is also included;

The cleaning system is used to clean the garbage and store it to the dust box;

Further, the binocular camera is an image sensor.

To solve the technical problem in the background art, the present invention also provides an image processing terminal, and the specific technical solutions are as follows:

An image processing terminal comprising an image processing system and a wireless communication system;

The wireless communication system is configured to receive two picture information transmitted externally;

The image processing system is configured to process two pieces of the picture information and obtain obstacle information;

The wireless communication system is further configured to transmit the obstacle information to the outside.

Further, the image processing terminal is a cloud server.

In order to solve the technical problem in the background art, the present invention also provides a sweeping robot system, and the specific technical solutions are as follows:

A cleaning robot system comprising any of the above-described cleaning robots having a wireless communication system and the image processing terminal of any of the above.

Further, the cleaning robot includes a binocular camera, a wireless communication system, and a control system;

Further, the cleaning robot further includes a driving system;

When the obstacle size of the obstacle information is greater than a preset value, the control system (150) controls the drive system to cause the sweeping robot to bypass the obstacle along the obstacle contour.

Further, the cleaning robot further includes a cleaning system;

The cleaning system is used to clean the garbage and store it to the dust box;

Further, the image processing terminal includes: an image processing system and a wireless communication system;

In order to solve the technical problem in the background art, the present invention also provides a working method of a cleaning robot, and the specific technical solutions are as follows:

A working method of a sweeping robot, comprising:

Obtaining two picture information of different angles of the same obstacle at the same time;

Obtaining obstacle information based on two pieces of the picture information;

Different working modes are selected based on the obstacle information.

Further, the step of acquiring two pieces of picture information of different angles of the same obstacle at the same time further includes:

Associate all obstacle information with the corresponding work mode.

Compared with the prior art, the beneficial effects of the present invention are:

The invention obtains obstacle information of the working environment of the sweeping robot through the binocular camera, and can acquire information such as the size of the obstacle, the shape of the obstacle, and the distance between the obstacle and the sweeping robot, so that the sweeping robot automatically judges whether it can be cleaned, whether it can be crossed, Whether it can be drilled, greatly improved the trapped situation of the sweeping robot, and improved the intelligent level and user experience of the sweeping robot.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly described below. It is obvious that the drawings in the following description are some embodiments of the present invention. For the ordinary technicians, other drawings can be obtained based on these drawings without any creative work.

1 is a schematic structural diagram of a cleaning robot according to an embodiment of the present invention;

2 is a schematic diagram of a module of the cleaning robot of FIG. 1;

FIG. 3 is a schematic diagram of another module of a cleaning robot according to an embodiment of the present invention; FIG.

4 is a schematic block diagram of an image processing terminal according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a module of a cleaning robot system according to an embodiment of the present invention; FIG.

FIG. 6 is a schematic structural diagram of a system for sweeping a robot according to an embodiment of the present invention; FIG.

FIG. 7 is a flowchart of a working method of a cleaning robot according to an embodiment of the present invention.

Reference numerals: 1 is a sweeping robot, 110 is a binocular camera, 120 is a driving system, 130 is a cleaning system, 140, 210 are image processing systems, 150 is a control system, 160 is a sensor system, 170 is a power system, 180, 220 is a wireless communication module, 2 is an image processing terminal, and 11, 12 are CCD cameras.

Detailed ways

The technical solutions of the present invention will be clearly and completely described in the following with reference to the accompanying drawings and specific embodiments. It is obvious that the embodiments described herein are only a part of the embodiments of the invention, but not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the specific embodiments described herein are intended to be within the scope of the invention as defined by the appended claims.

Example 1

1-2, FIG. 1 is a schematic structural diagram of a cleaning robot according to an embodiment of the present invention; and FIG. 2 is a schematic diagram of a module of the cleaning robot in FIG.

The cleaning robot 1 in this embodiment includes a control system 150, a driving system 120, a cleaning system 130, a sensor system 160, a power supply system 170, and a binocular camera 110 (the binocular camera 110 is an image sensor, which includes a left CCD in this embodiment). Camera 11, right CCD camera 12) and image processing system 140. In the case where the environment is relatively simple, for the sake of cost and speed, the CCD (charcode coupled device, ie, charge coupled device) may be replaced by CMOS (Complementary Metal Oxide Semiconductor).

The control system 150 includes an MCU or a single chip microcomputer (in this embodiment, an MCU with a memory) storing a working program of the cleaning robot 1, the control system 150 performing different actions according to the obstacle information; that is, according to the sensor system 160 or image processing The obstacle information returned by the system 140 controls the driving system 120 and the cleaning system 130 to operate; the binocular camera 110 is used to acquire two picture information of different angles of the same obstacle at the same time; the image processing system 140 is used for the binocular camera 110 The acquired two pieces of picture information are processed to obtain obstacle information; the driving system 120 includes left and right driving wheels for driving the cleaning robot 1 to move in the working area; the cleaning system 130 includes a middle sweeping, vacuuming device, side sweeping and dust box For cleaning the ground garbage and storing it to the dust box; the sensor system 160 includes a ground inspection and a wall inspection for respectively detecting a surface area difference and surrounding obstacles (including walls); the power system 170 is used for each of the cleaning robots 1 The system provides electrical energy, typically a rechargeable battery (such as a lithium battery).

The obstacle information includes the size of the obstacle, the shape of the obstacle, and the distance between the obstacle and the cleaning robot 1

The binocular camera 110 includes a left CCD camera 11 and a right CCD camera 12, and the left and right cameras are relatively fixedly mounted on the front side of the main body of the cleaning robot 1, and the left CCD camera 11 and the right CCD camera 12 are substantially on the same horizontal plane (with the calibration model algorithm) In this embodiment, the Opencv needs to ensure that the optical axes of the dual cameras are parallel in the physical structure. At the same time, the cameras respectively acquire the horizontal range of the forward direction from 150° to 180° and the vertical direction from 90° to 120°. Two pictures of different angles of the obstacle. The left CCD camera 11 and the right CCD camera 12 of the binocular camera 110 perform stereo calibration before the cleaning robot 1 is shipped from the factory, and the rotation matrix R and the translation matrix t between the left CCD camera 11 and the right CCD camera 12 can be obtained by Zhang Zhengyou calibration method. Got it. The binocular camera 110 can be an image sensor.

In this embodiment, the process of identifying the distance and size of the obstacle is as follows:

This embodiment is based on the Opencv platform and uses the SGBM algorithm provided by Opencv for matching calculation. Firstly, the left and right CCD cameras are stereo-matched at the same time, then the original image is binarized, Gaussian blur, canny operator contour detection, the obstacle contour is found, and the obstacle is completely framed by the minimum quadrilateral. The coordinates of the four vertices of the quadrilateral obtain the pixel size of the obstacle; the pixel coordinates of the center point of the object are obtained by calculating the coordinates of the four vertices of the quadrilateral, and the distance between the center point of the obstacle and the camera is obtained by the binocular ranging principle. According to the triangle principle, The width and height of the obstacle are calculated to measure the size of the obstacle.

Specifically, first use reprojectImageTo3D to generate a 3D point cloud, use findContours to obtain the obstacle contour, traverse to delete the maximum and minimum contours, use minAreaRect to obtain the minimum proof of the contour and get the coordinates of the four vertices of the rectangle, and then calculate the obstacle by trigonometric function. Size (length, width, height, etc.).

In this embodiment, the program stored by the controller (MCU with memory) is associated with common static objects (such as furniture, home appliances or thresholds) and dynamic objects (such as people or pets) in the indoor environment, that is, each of the indoor environments. Objects (obstacle) are associated with corresponding work patterns and perform different actions when different obstacles are identified, such as when identifying objects with lower heights such as thresholds, slippers, or cables (by setting a height threshold, such as The current climbing height of the sweeping robot 1 is about 2 cm. When the obstacle height is greater than 2 cm, the obstacle is marked as non-cross-domain. When the sweeping robot 1 moves to the vicinity of the obstacle, the obstacle is no longer carried out. When the sweeping robot 1 moves to the vicinity of the obstacle, the driving force of the driving system 120 is increased and the crossing action is performed; when the obstacle is recognized as the felt, the crossing operation is performed while increasing the cleaning system 130 The driving force of the suction and driving system 120; when the obstacle is identified as garbage, the cleaning robot 1 drives to the garbage and cleans; the obstacle is recognized as the height of the person or the refrigerator Higher object, the cleaning robot 1 performs avoidance operation or the like. This setting makes the cleaning robot 1 work smarter and improves the user experience.

Example 2

Referring to FIG. 3-6, FIG. 3 is a schematic diagram of another module of a cleaning robot according to an embodiment of the present invention; FIG. 4 is a schematic diagram of a module of an image processing terminal according to an embodiment of the present invention; A schematic diagram of a module of a cleaning robot system is provided. FIG. 6 is a schematic structural diagram of a system for sweeping a robot according to an embodiment of the present invention.

As shown in FIG. 3, the cleaning robot 1 in this embodiment includes a control system 150, a driving system 120, a cleaning system 130, a sensor system 160, a power supply system 170, and a binocular camera 110. The binocular camera 110 is an image sensor. The example includes a left CCD camera 11, a right CCD camera 12), and a wireless communication system. In the case where the environment is relatively simple, for the sake of cost and speed, the CCD (charcode coupled device, ie, charge coupled device) may be replaced by CMOS (Complementary Metal Oxide Semiconductor).

The cleaning robot 1 in this embodiment is basically the same as that in the first embodiment, and the difference is that: A, the cleaning robot 1 in this embodiment does not have the image processing system 140; B, the cleaning robot 1 in this embodiment will double The two picture information acquired by the camera 110 are sent to the image processing terminal 2 through the wireless communication module 180 (such as a WIFI module or a Zigbee module) to process the two pieces of image information.

The functions and functions of the cleaning robot 1 in the present embodiment are the same as those of the control system 150, the drive system 120, the cleaning system 130, the sensor system 160, the power supply system 170, and the binocular camera 110 of the cleaning robot 1 in the first embodiment. The examples are not described in detail, and refer to Example 1 for details.

The wireless communication module 180 is configured to transmit the two pieces of the picture information to the outside, and is further configured to receive the externally transmitted obstacle information, and transmit the obstacle information to the control system 150, so that the control system 150 performs different actions according to the obstacle information. That is, the drive system 120 and the cleaning system 130 are controlled to operate based on the obstacle information returned by the sensor system 160 or the image processing system 210.

As shown in FIG. 4, the image processing terminal 2 in this embodiment is a cloud server (other PC platform or embedded platform capable of image processing capability of the binocular camera 110), and includes an image processing system 210 and a wireless communication module 220. The wireless connection network between the cloud server and the cleaning robot 1 includes a 4G, a WIFI network, and the like, and the networking mode includes an AP mode (wireless access point) or an STA mode (STA site).

The process of identifying the distance and the size of the obstacle in this embodiment is the same as that in the first embodiment. This embodiment is not described in detail. For details, refer to the embodiment 1.

As shown in FIG. 5-6, the obstacle recognition process in this embodiment is as follows: the binocular camera 110 of the cleaning robot 1 acquires two picture information of different angles of the same obstacle at the same time, and wireless communication by the cleaning robot 1 The module 180 transmits the two picture information to the wireless communication module 220 of the image processing terminal 2, and the image processing system 210 of the image processing terminal 2 processes the two picture information to obtain obstacle information, and passes through the wireless communication module of the image processing terminal 2. The obstacle information is transmitted to the wireless communication module 180 of the cleaning robot 1, and the control system 150 of the cleaning robot 1 controls the driving system 120 and the cleaning system 130 to operate based on the obstacle information. Two of the picture information and obstacle information can be transmitted via the internet. The image processing terminal is preferably a cloud server.

Example 3

Please refer to FIG. 7. FIG. 7 is a flowchart of a working method of a cleaning robot according to an embodiment of the present invention.

As shown in FIG. 7, the working method of a cleaning robot in this embodiment includes the following steps S100 to S400:

Step S100: Associate all obstacle information with a corresponding working mode.

Specifically, the feature information such as the shape and color of the obstacles commonly found in the indoor environment where the cleaning robot is located is associated with the corresponding working mode, and the controller of the cleaning robot selects different working modes according to the feedback obstacle information. For example, when the garbage feature is met, the sweeping robot drives toward the obstacle and increases the suction or rolling speed of the cleaning system; when the carpet features are met, the driving force of the driving system is increased while increasing the suction or rolling speed of the cleaning system. If the water lag feature is met, the avoidance action is performed.

Step S200: Acquire two picture information of different angles of the same obstacle at the same time.

Specifically, the front side of the forward direction of the sweeping robot is mounted at substantially the same height to mount the binocular camera (the left CCD camera 11 and the right CCD camera 12), and the camera captures the horizontal direction of the forward direction by 150° to 180° at the same time. Two pictures of different angles of obstacles in the vertical direction from 90° to 120°.

Step S300: Obtain obstacle information based on the two pieces of the picture information.

Specifically, after the acquired two pictures are sent to the image processing system for processing (the process is described with reference to Embodiment 1), obstacle information including an obstacle size, an obstacle shape, and a distance from the cleaning robot is obtained, and then The obstacle information is sent to the control system of the cleaning robot. As described in Embodiment 1, Embodiment 2, the image processing system may be mounted on a cleaning robot or on a cloud server.

Step S400: Select different working modes based on the obstacle information.

Specifically, when it is determined whether the height of the obstacle is greater than a preset value, if yes, the sweeping robot performs an avoidance action when moving to the vicinity of the obstacle, and if otherwise, the sweeping robot continues to move in the original direction. That is, when the obstacle size of the obstacle information is not greater than a preset value, the control system controls the driving system to increase the driving force, so that the sweeping robot crosses the obstacle; when the obstacle information size of the obstacle information is greater than the preset In value, the control system controls the drive system to cause the sweeping robot to bypass the obstacle along the obstacle profile. It is also possible to judge whether or not the obstacle has a space through which the sweeping robot can pass, and if so, the sweeping robot continues to move in the original direction, otherwise the sweeping robot performs the avoidance action after moving to the vicinity of the obstacle. Specifically, it is determined whether there is a space for the cleaning robot to pass through the shape of the obstacle, and then it is judged whether the height and the width of the cover space are larger than the height and width of the cleaning robot, and the space is considered to be available under the condition that both the height and the width are satisfied at the same time. The sweeping robot passes through. When the current obstacle is determined to be a blanket based on the obstacle information, the control system controls the driving system to increase the driving force, causing the cleaning robot to cross the blanket; and controlling the cleaning system to increase the cleaning power; When the obstacle information determines that the current obstacle is garbage, the control system controls the driving system to move the cleaning robot to the garbage; and controls the cleaning system to perform cleaning. The obstacle information includes the size of the obstacle, the shape of the obstacle, and the distance between the obstacle and the sweeping robot.

The technical features of the above-described embodiments may be arbitrarily combined. For the sake of brevity of description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, All should be considered as the scope of this manual.

The above-described embodiments are merely illustrative of several embodiments of the present invention, and the description thereof is more specific and detailed, but is not to be construed as limiting the scope of the invention. It should be noted that a number of variations and modifications may be made by those skilled in the art without departing from the spirit and scope of the invention. Therefore, the scope of the invention should be determined by the appended claims.

Claims

A sweeping robot, comprising a control system (150), characterized in that:

Also included is a binocular camera (110) and an image processing system (140);

The binocular camera (110) is configured to acquire two picture information of different angles of the same obstacle at the same time;

The image processing system (140) is configured to process two picture information acquired by the binocular camera and obtain obstacle information;

The control system performs different actions based on the obstacle information.
The cleaning robot according to claim 1, wherein:

The obstacle information includes an obstacle size, an obstacle shape, and a distance between the obstacle and the sweeping robot.
The cleaning robot according to claim 2, further comprising a driving system (120);

The driving system (120) is configured to drive the cleaning robot to move in a working area;

When the obstacle size of the obstacle information is not greater than a preset value, the control system (150) controls the driving system (120) to increase the driving force, so that the cleaning robot crosses the obstacle;

When the obstacle size of the obstacle information is greater than a preset value, the control system (150) controls the drive system (120) to cause the sweeping robot to bypass the obstacle along the obstacle contour.
The cleaning robot according to claim 3, further comprising a cleaning system (130);

The cleaning system (130) is used to clean the garbage and store it to the dust box;

When determining that the current obstacle is a blanket based on the obstacle information, the control system (150) controls the driving system (120) to increase the driving force, causing the cleaning robot to cross the blanket; and controlling the cleaning system (130) to increase. Clean power

When it is determined that the current obstacle is garbage based on the obstacle information, the control system (150) controls the driving system (120) to move the cleaning robot to the garbage; and controls the cleaning system (130) to perform cleaning.
The cleaning robot according to claim 1, wherein:

The binocular camera (110) is an image sensor.
The cleaning robot according to claim 1, wherein:

The binocular camera (110) is relatively fixedly mounted on the front end surface of the cleaning robot and the two cameras of the binocular camera are installed at the same horizontal position.
A sweeping robot characterized by comprising a binocular camera (110), a wireless communication system (180) and a control system (150);

The binocular camera (110) is configured to acquire two picture information of different angles of the same obstacle at the same time;

The wireless communication system (180) is configured to transmit two pieces of the picture information to the outside, and is further configured to receive externally transmitted obstacle information;

The control system (150) performs different actions based on the obstacle information.
A cleaning robot according to claim 7, wherein:

The obstacle information includes an obstacle size, an obstacle shape, and a distance between the obstacle and the sweeping robot.
The sweeping robot according to claim 8, further comprising a drive system (120);

The driving system (120) is configured to drive the cleaning robot to move in a working area;

When the obstacle size of the obstacle information is not greater than a preset value, the control system controls (150) the driving system (120) to increase the driving force, so that the sweeping robot crosses the obstacle;

When the obstacle size of the obstacle information is greater than a preset value, the control system (150) controls the drive system (120) to cause the sweeping robot to bypass the obstacle along the obstacle contour.
The cleaning robot according to claim 9, further comprising a cleaning system (130);

The cleaning system (130) is used to clean the garbage and store it to the dust box;

When determining that the current obstacle is a blanket based on the obstacle information, the control system (150) controls the driving system (120) to increase the driving force, causing the cleaning robot to cross the blanket; and controlling the cleaning system (130) to increase. Clean power

When it is determined that the current obstacle is garbage based on the obstacle information, the control system (150) controls the driving system (120) to move the cleaning robot to the garbage; and controls the cleaning system (130) to perform cleaning.
A cleaning robot according to claim 7, wherein:

The binocular camera (110) is an image sensor.
A cleaning robot according to claim 7, wherein:

The binocular camera (110) is relatively fixedly mounted on the front end surface of the cleaning robot and the two cameras of the binocular camera are installed at the same horizontal position.
An image processing terminal, comprising: an image processing system (210) and a wireless communication system (220);

The wireless communication system (220) is configured to receive two picture information transmitted externally;

The image processing system (210) is configured to process two pieces of the picture information and obtain obstacle information;

The wireless communication system (220) is further configured to transmit the obstacle information to the outside.
The terminal of claim 13 wherein:

The image processing terminal is a cloud server.
A sweeping robot system characterized by comprising a cleaning robot (1) and an image processing terminal (2).
The system of claim 13 wherein:

The cleaning robot includes a binocular camera (110), a wireless communication system (180), and a control system (150);

The binocular camera (110) is configured to acquire two picture information of different angles of the same obstacle at the same time;

The wireless communication system (180) is configured to transmit two pieces of the picture information to the outside, and is further configured to receive externally transmitted obstacle information;

The control system (150) performs different actions based on the obstacle information.
The system according to claim 16, wherein said cleaning robot further comprises a drive system (120);

The driving system (120) is configured to drive the cleaning robot to move in a working area;

When the obstacle size of the obstacle information is not greater than a preset value, the control system controls (150) the driving system (120) to increase the driving force, so that the sweeping robot crosses the obstacle;

When the obstacle size of the obstacle information is greater than a preset value, the control system (150) controls the drive system (120) to cause the sweeping robot to bypass the obstacle along the obstacle contour.
The system of claim 16 wherein said cleaning robot further comprises a cleaning system (130);

The cleaning system (130) is used to clean the garbage and store it to the dust box;

When judging that the current obstacle is a blanket based on the obstacle information, the control system (150) controls the driving system (120) to increase the driving force, causing the cleaning robot to cross the blanket; and controlling the cleaning system (130) to increase Clean power

When it is determined that the current obstacle is garbage based on the obstacle information, the control system (150) controls the driving system (120) to move the cleaning robot to the garbage; and controls the cleaning system (130) to perform cleaning.
The system of claim 16 wherein:

The binocular camera (110) is relatively fixedly mounted on the front end surface of the cleaning robot and the two cameras of the binocular camera are installed at the same horizontal position.
The system of claim 15 wherein:

The image processing terminal includes: an image processing system (210) and a wireless communication system (220);

The wireless communication system (220) is configured to receive two picture information transmitted externally;

The image processing system (210) is configured to process two pieces of the picture information and obtain obstacle information;

The wireless communication system (220) is further configured to transmit the obstacle information to the outside.
A working method of a sweeping robot, characterized in that it comprises:

Obtaining two picture information of different angles of the same obstacle at the same time;

Obtaining obstacle information based on two pieces of the picture information;

Different working modes are selected based on the obstacle information.
A method of operating a cleaning robot according to claim 21, wherein:

The obstacle information includes an obstacle size, an obstacle shape, and a distance between the obstacle and the sweeping robot.
The working method of the cleaning robot according to claim 21, wherein the step of acquiring two pieces of picture information of different angles of the same obstacle at the same time further comprises: all obstacle information and corresponding working mode Associated.